High Explainability
High explainability in artificial intelligence (AI) aims to make the decision-making processes of complex models, such as large language models and deep neural networks, more transparent and understandable. Current research focuses on developing both intrinsic (built-in) and post-hoc (added after training) explainability methods, often employing techniques like attention mechanisms, feature attribution, and counterfactual examples to interpret model outputs across various modalities (text, images, audio). This pursuit is crucial for building trust in AI systems, particularly in high-stakes domains like medicine and finance, and for ensuring fairness, accountability, and responsible AI development.
Papers
Evaluating the Explainability of Attributes and Prototypes for a Medical Classification Model
Luisa Gallée, Catharina Silvia Lisson, Christoph Gerhard Lisson, Daniela Drees, Felix Weig, Daniel Vogele, Meinrad Beer, Michael Götz
Explainable Generative AI (GenXAI): A Survey, Conceptualization, and Research Agenda
Johannes Schneider
Mining Potentially Explanatory Patterns via Partial Solutions
GianCarlo Catalano, Alexander E. I. Brownlee, David Cairns, John McCall, Russell Ainslie
Influence based explainability of brain tumors segmentation in multimodal Magnetic Resonance Imaging
Tommaso Torda, Andrea Ciardiello, Simona Gargiulo, Greta Grillo, Simone Scardapane, Cecilia Voena, Stefano Giagu
An ExplainableFair Framework for Prediction of Substance Use Disorder Treatment Completion
Mary M. Lucas, Xiaoyang Wang, Chia-Hsuan Chang, Christopher C. Yang, Jacqueline E. Braughton, Quyen M. Ngo
Explaining Explainability: Understanding Concept Activation Vectors
Angus Nicolson, Lisa Schut, J. Alison Noble, Yarin Gal